{"id":"W4401024942","doi":"10.24963/ijcai.2024/630","title":"SIFAR: A Simple Faster Accelerated Variance-Reduced Gradient Method","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Renmin University of China; National Natural Science Foundation of China; University of Oxford; Royal Society; Institute for Catastrophic Loss Reduction","keywords":"Minimax; Generalization; Mathematical optimization; Mathematics; Saddle point; Stochastic gradient descent; Applied mathematics; Generalization error; Dimension (graph theory); Computer science; Upper and lower bounds; Combinatorics; Artificial intelligence; Artificial neural network; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006156116,0.0006119416,0.0006016743,0.0006162045,0.0001050142,0.001167866,0.002438514,0.0004319362,0.0002515062],"category_scores_gemma":[0.0001018266,0.0005427065,0.0002797978,0.0009689823,0.00004655167,0.0002015473,0.006179683,0.000967043,0.000217599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002405405,"about_ca_system_score_gemma":0.000370241,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001374993,"about_ca_topic_score_gemma":0.000006336562,"domain_scores_codex":[0.9961484,0.0001868372,0.0007401823,0.001762371,0.0005636169,0.0005985639],"domain_scores_gemma":[0.9970722,0.0001760749,0.0002516015,0.001928462,0.0003395077,0.0002321972],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001274085,0.000226674,0.000007885937,0.000366371,0.0003809808,0.00009357805,0.002585366,0.02144852,0.001479182,0.884669,0.04073016,0.04799956],"study_design_scores_gemma":[0.0001448244,0.00006627061,0.00002115441,0.0001299938,0.00004784945,0.00003186673,0.00001509591,0.702102,0.006814938,0.288505,0.001517253,0.00060382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000221259,0.0001587769,0.9760563,0.001872541,0.002489207,0.001065761,0.00002806818,0.003541411,0.01456666],"genre_scores_gemma":[0.05119788,0.00001988516,0.9443495,0.0008182649,0.0001744044,0.0005094049,0.00006812829,0.00007395487,0.002788551],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6806535,"threshold_uncertainty_score":0.999869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05201765390773348,"score_gpt":0.3303637942119841,"score_spread":0.2783461403042506,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}